CN106408940A - Microwave and video data fusion-based traffic detection method and device - Google Patents
Microwave and video data fusion-based traffic detection method and device Download PDFInfo
- Publication number
- CN106408940A CN106408940A CN201610952272.0A CN201610952272A CN106408940A CN 106408940 A CN106408940 A CN 106408940A CN 201610952272 A CN201610952272 A CN 201610952272A CN 106408940 A CN106408940 A CN 106408940A
- Authority
- CN
- China
- Prior art keywords
- video
- data
- sensor
- target
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Radar Systems Or Details Thereof (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a microwave and video data fusion-based traffic detection device. The microwave and video data fusion-based traffic detection device comprises a video sensor, a microwave sensor, an A/D conversion module, a processor module, a network communication module, a traffic flow parameter data fusion module, a traffic flow management platform, a target tracking module and a traffic event and information management platform. The invention also discloses a microwave and video data fusion-based traffic detection method. According to the method, the device is adopted to realize information complementation and data fusion. With the device of the invention adopted, the reliability of a system can be improved, the accurate estimation of the position of a target can be provided, more accurate data can be obtained, and powerful parameters can be provided for relevant departments. According to the microwave and video data fusion-based traffic detection method, after the microwave sensor detects some traffic behaviors which are inputted into a database, the video sensor is controlled to take pictures, and then, whether obtained data are matched with the data of the database is analyzed, an alarm is given, and therefore, false alarm rate can be reduced, human and material resources can be reduced, and intelligent detection can be realized actually.
Description
Technical field
The invention belongs to intelligent transportation field, more particularly it relates to a kind of melted based on microwave and video data
The Vehicle Detection method and device closed.
Background technology
Data fusion mainly has data level, feature level and three kinds of modes of decision level fusion.Pixel-based fusion refers to merging
It is desirable to the sensing data being merged has the fusion of any information of the matching precision being accurate to a pixel in algorithm；
Feature-based fusion refers to carry out feature extraction from the initial data that each sensor provides, and then merges these features；Decision-making
Level fusion refers to that each sensing data source is all passed through and converted and obtain independent identity estimation before merging.
Data fusion process includes target detection, data association, tracking and identification, situation estimation and the conjunction of multisensor
And.Data fusion is that the Incomplete information with regard to a certain environmental characteristic that multiple sensors and information source are provided is in addition comprehensive
Close, to form relatively complete, consistent perception description, thus realizing more accurately identifying arbitration functions.Obtained by merging
Than each input data single, more information, due to the collective effect of more multisensor, make the effectiveness of system be increased
By force.
The design of multisensor syste equipment and the productivity improve so that sensor performance greatly improves, and how to process number
Amount is huge, and miscellaneous information becomes the problem that multisensor syste first has to consider.Particularly have uncertain in information
Property in the case of, be the process that data obtained to single-sensor or information are carried out with respect to single-sensor data processing,
There may be partly imperfect or insecure information, Fusion can comprehensively utilize multisensor letter effectively
Breath, such that it is able to obtaining more accurate, the complete information of detected target and environment to a great extent and conforming retouching
State or understand.
Microwave remote sensor is a kind of radar installations for round-the-clock monitoring traffic.It can measure the microwave area of coverage
The distance of target in domain, azimuth, speed, size etc., it is provided that the complete positional information of target and doppler information, by this
A little measurement to realize the detection of the vehicle to multilane and pedestrian.When being detected, microwave remote sensor receives returning of reflection
Ripple signal, carries out background suppression to echo-signal, extracts useful signal, is capable of detecting when telecommunication flow information, in target acquisition
Play important function with tracking aspect.Shortcoming is can not intuitively to see the kinestate of target as video, and
The judgement of the information such as the license plate number of vehicle, color.
Video frequency vehicle sensor is as video sensor using video camera, is a kind of based on video image analysis and calculating
Machine vision technique road pavement runs the integrated system that vehicle is tested and analyzed, and the method real-time monitoring using Image Engineering is divided
The traffic image of analysis input, can detect traffic dynamic behavior and various traffic data, including traffic flow, vehicle classification, account for
There are rate, speed, queue length, license plate number, body color etc..Shortcoming is to be limited by live lighting condition, current image procossing
Real-time is poor, and accuracy of detection is limited by whole system software and hardware.
Content of the invention
The invention discloses a kind of Vehicle Detection method and device, the method and dress being merged based on microwave and video data
Put and can more accurately monitor traffic behavior state and statistics telecommunication flow information, it is achieved thereby that the mobilism of general communication system is excellent
Change and run, effectively meet the transport need that the public constantly expands.
The technical solution adopted in the present invention is：
A kind of Vehicle Detection device being merged based on microwave and video data, described device includes video sensor, microwave
Sensor, A/D modular converter, processor module, network communication module, traffic flow parameter data fusion module, traffic flow management
Platform, target tracking module, traffic events and information management platform；
Described video sensor is connected with described A/D modular converter respectively with described microwave remote sensor, video sensor
With the non-electric charge quantity signalling of the different characteristic of microwave remote sensor output, it is then passed through described A/D modular converter and converts them to energy
Digital quantity by computer disposal；Described A/D modular converter is connected with described processor module, described processor module with described
Network communication module connects, and described processor module enters to via the data that described A/D module processing is converted into digital quantity
Row is processed, and filters some abnormal datas to obtain useful signal, useful signal is transmitted by described network communication module again；
Described network communication module is connected with described traffic flow parameter data fusion module, described target tracking module respectively
Connect, useful signal is transferred to described traffic flow parameter data fusion module, described target following mould by described network communication module
Block；
Described traffic flow parameter data fusion module and described traffic flow management platform connect, described traffic flow parameter data
Fusion Module carries out space-time uniformity, feature extraction to useful signal, and based on data fusion being carried out to characteristic quantity by certain rule
Calculate, finally export fusion results to described traffic flow management platform；
Described target tracking module and traffic events are connected with information management platform, and described target tracking module is to useful letter
Number carry out space-time uniformity, feature extraction, and by certain rule, data fusion calculating is carried out to characteristic quantity, finally by fusion results
Export to described information management platform.
A kind of Vehicle Detection method being merged based on microwave and video data, is comprised the steps of：
The first step：Detection, carries out background noise suppression respectively in two sensors detection zone, export traffic flow, put down
All speed, occupation rate, queue length and other instant messages；
Second step：Initial data pretreatment, is standardized and carries out pretreatment to multigroup sensing data of input, full
The requirement to amount of calculation and computation sequence of sufficient subsequent estimation and processor module；
Grubbs statistical method is adopted for abnormal data preprocess method；
3rd step：Space-time is calibrated, and calibrates time and the spatial reference point of unified each sensor, snaps to same in time
Time reference, spatially it is transformed into the same coordinate system, set up coordinate corresponding relation so that the result after processing seems data
It is the same that fusion treatment central station is gathered；If each sensor is independently asynchronous working over time and space, must enter
The row time moves and coordinate transform, merges required unified time and spatial reference point to be formed；By to single sensor
The position of acquisition is merged with the estimated information of identity category, obtains more accurate target location, state and identity category
Estimation；
4th step：Basic dynamic traffic Parameter fusion, can detect from video sensor and microwave remote sensor simultaneously
The basis such as the traffic flow on section, average speed, occupation rate, queue length traffic parameter carries out fusion treatment, draws more accurate
Really reliable traffic flow parameter；The fusion results of this level are the inputs of next emerging system simultaneously；
5th step：Data association, differentiates whether the data in different time space is derived from same target, radar and video object
Mated, real target can be defined as by successful match, processed by setting means it is impossible to the target of coupling is it is believed that can not be true
Fixed target is it is impossible to exclude the possibility；Using the distance of target, orientation, relative velocity as parameter, calculate radar target and video
The association angle value of target, when associating angle value and being more than the threshold value setting it is believed that mating；The correlation that same sensor is observed and predicted in succession
Data carries out synthesis and state estimation, and with reference to the checking that data is modified of observing and predicting in other information source, each sensor is passed
The point mark sent is associated, and keeps target is continuously followed the tracks of；
6th step：Target recognition and tracking；Form the spy of a N-dimensional according to a certain target characteristic that different sensors record
Levy vector, often an one-dimensional independent characteristic representing target, is compared with consistent feature, so that it is determined that the classification of target.
New data set is just merged by the end of scan with original data every time, and the observation according to sensor estimates target component,
And estimate the position of target in prediction scanning next time with these；
7th step：Traffic behavior is estimated；Detections of radar, to target, exports three-dimensional coordinate, controls video monitoring output image,
According to video coordinates model and radar and the position relationship of video, using 2 points of lowest distance value d of A, B as matching condition, make
The information obtaining the same object that two sensors detect corresponds to, and is gone out for same target with match cognization from synchronous images.
Which kind of the data set of all targets is compared with the behavioral pattern of previously determined possible situation, so that determined behavioral pattern and prison
In viewed area, the state of all targets is mated most, is saved in traffic information platform by same for these information.
Preferably, in described second step, described had with Grubbs statistical method for abnormal data preprocess method
Body is as follows：
Calculate each detection data Z of outputiAverage
Calculate standard deviation
Calculate Grubbs statistic
Give according to data volume n, significant level a=0.05, find out marginal value T of Grubbs statistic by look-up table
(n a), is compared with T；It is small probability event according to P [T >=T (n, a)]=a, give up T >=T (n, data a).
Preferably, in described 3rd step, the establishment step of coordinate corresponding relation is as follows：
First, calculate the inner parameter of video sensor using calibration technique, set up video sensor coordinate model；
Secondly, according to the position relationship between video sensor coordinate model and microwave remote sensor and video sensor,
Set up coordinate in video sensor acquired image plane for the target that microwave remote sensor under world coordinate system monitored
Corresponding relation；
Finally, the information of microwave remote sensor just can be realized according to coordinate corresponding relation and video information is merged, real
The 3D world coordinates that existing microwave remote sensor detects is converted into corresponding 2D image coordinate p ' (u ', v ') in video image, with abundant
The positional information correspondence being monitored using microwave remote sensor is to video image.
Preferably, in described 4th step, for same object of observation, the result of different sensors output can not
Same, in the case of there is no priori, take following methods to carry out data fusion：
Using adaptive optimal Weighted Fusion model, if the traffic flow data variance of two sensors is respectively σ1、σ2, institute
True value to be estimated is X, and the measured value of each sensor is respectively X1、X2, they are independent each other, and are that the unbiased of X is estimated
Meter；The weighter factor of each sensor is respectively W1、W2, then the measured value after fusionFor：
Wherein
The method can require no knowledge about any priori of this two detection measurement data, simply applies multisensor
The detection data providing the minimum data fusion value of mean value error it is possible to merge.
Preferably, Fuzzy Synthetical Decision Model is adopted to construct a traffic events recognizer, step in described 7th step
As follows：
A1, traffic behavior are estimated, set up model library, to the traffic abnormity state modeling generally occurring within, are easy to record
Pattern match in behavioral pattern and data base；
A2, monitor in real time pavement state, carry out monitor in real time by microwave remote sensor 2 and video sensor 1；
A3, there is the judgement of situation in monitoring range by radar, if it has not, then return A2 proceeding in real time
Monitoring pavement state, if it has, then enter next step；
A4, the three-dimensional coordinate of outgoing event target, the current synchronous images of video acquisition；Radar and video information merge,
Three-dimensional coordinate is mapped to the radar detection coordinate in synchronous images, sends early warning information, and regarded by video sensor 1
Frequency gathers current synchronous images；
A5, radar and video information merge, and three-dimensional coordinate mapping is obtained the radar detection coordinate in synchronous images；
A6, in world coordinate system, set up the matching relationship of radar detection coordinate and image detection target, from synchronous images
In identify event information；
The information such as the picture of A7, output traffic events type and event vehicle, license plate number are to traffic events and information management
Management platform.
After technique scheme, in the present invention, video and radar complex are using composition radar-video multisensor system
System, using message complementary sense, by Data fusion technique, becomes detection means of tracking that is separate and supplementing each other, Neng Gouti
High system reliability can provide the accurate estimation to target location；Melted by the telecommunication flow information that each sensor detects
Conjunction is processed, and obtains more precisely data, provides strong parameter for relevant department；Taken by video based on detections of radar
Supplemented by card, traffic behavior state is estimated, event information is carried out with alarm and captures evidence obtaining；The present invention proposes to be based on
The fusion method of microwave and video data, after carrying out pretreatment to the initial data of both sensors, through space-time
Unified, draw standardized characteristic information；In data fusion module, by using the decision making level data fusion side based on weights
Method, exports more accurate telecommunication flow information；After microwave remote sensor detects some traffic behaviors of typing in data base, control
Whether video sensor is taken pictures, then be analyzed mating with data base, is reported to the police, and reduces false alarm rate, reduces manpower
Material resources, are truly realized intellectualized detection.
Brief description
Fig. 1 is the schematic block diagram of the Vehicle Detection device that the present invention is merged based on microwave and video data；
Fig. 2 is microwave and the schematic block diagram of video data fusion method；
Fig. 3 is the schematic block diagram of data preprocessing method；
Fig. 4 be the traffic behavior method of estimation that merged based on microwave and video data show that frame is intended to.
Specific embodiment
Purpose, technical scheme and advantage for making the embodiment of the present invention are clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described.Following examples are only used for more clear
Chu's ground explanation technical scheme, and can not be limited the scope of the invention with this.
A kind of Vehicle Detection device being merged based on microwave and video data, as shown in figure 1, described device includes video pass
Sensor 1, microwave remote sensor 2, A/D modular converter 3, processor module 4, network communication module 5, traffic flow parameter data fusion mould
Block 6, traffic flow management platform 7, target tracking module 8, traffic events and information management platform 9, video sensor 1 and microwave pass
Sensor 2 is connected with A/D modular converter 3 respectively, the non electrical quantity of the different characteristic of video sensor 1 and microwave remote sensor 2 output
Signal, being then passed through that A/D modular converter 3 converts them to can be by the digital quantity of computer disposal；A/D modular converter 3 and place
Reason device module 4 connects, and processor module 4 is connected with network communication module 5, and processor module 4 is at via A/D modular converter 3
The data that reason is converted into digital quantity is processed, and filters some abnormal datas to obtain useful signal, useful signal is again by net
Network communication module 5 is transmitted；Network communication module 5 respectively with traffic flow parameter data fusion module 6, target tracking module 8
It is connected, useful signal is transferred to traffic flow parameter data fusion module 6, target tracking module 8 by network communication module 5；Hand over
Through-flow supplemental characteristic Fusion Module 6 and traffic flow management platform 7 connect, and traffic flow parameter data fusion module 6 is to useful signal
Carry out space-time uniformity, feature extraction, and by certain rule, data fusion calculating is carried out to characteristic quantity, finally that fusion results are defeated
Go out to traffic flow management platform 7；Target tracking module 8 and traffic events are connected with information management platform 9, target tracking module 8
Useful signal is carried out with space-time uniformity, feature extraction, and by certain rule, data fusion calculating is carried out to characteristic quantity, finally will
Fusion results export to information management platform.
As shown in Fig. 2 Fig. 4, illustrate to based on the Vehicle Detection method that microwave and video data merge below, a kind of
Flow process as shown in Figure 2 is included based on the Vehicle Detection method that microwave and video data merge, as follows：
The first step：Detection, carries out background noise suppression respectively in two sensors detection zone, export traffic flow, put down
All speed, occupation rate, queue length and other instant messages；
Second step：Initial data pretreatment, is standardized and carries out pretreatment to multigroup sensing data of input, full
The requirement to amount of calculation and computation sequence of sufficient subsequent estimation and processor module 4；
For abnormal data preprocess method Grubbs statistical method；
Circular is as follows：
Calculate each detection data Z of outputiAverage
Calculate standard deviation
Calculate Grubbs statistic
Give according to data volume n, significant level a=0.05, find out marginal value T of Grubbs statistic by look-up table
(n a), is compared with T；It is small probability event according to P [T >=T (n, a)]=a, give up T >=T (n, data a)；
3rd step：Space-time is calibrated, and calibrates time and the spatial reference point of unified each sensor, snaps to same in time
Time reference, spatially it is transformed into the same coordinate system, set up coordinate corresponding relation so that the result after processing seems data
It is the same that fusion treatment central station is gathered；If each sensor is independently asynchronous working over time and space, must enter
The row time moves and coordinate transform, merges required unified time and spatial reference point to be formed；By to single sensor
The position of acquisition is merged with the estimated information of identity category, obtains more accurate target location, state and identity category
Estimation；
The establishment step of coordinate corresponding relation is：Calculate the inner parameter of video sensor 1 using calibration technique, foundation regards
Video sensor 1 coordinate model；According between video sensor 1 coordinate model and microwave remote sensor 2 and video sensor 1
Position relationship, sets up the target that under world coordinate system, microwave remote sensor 2 is monitored and puts down in video sensor 1 acquired image
Coordinate corresponding relation in face；Information and the video information of microwave remote sensor 2 just can be realized finally according to coordinate corresponding relation
Merged, the 3D world coordinates realizing microwave remote sensor 2 detection is converted into corresponding 2D image coordinate p ' in video image
(u ', v '), to make full use of the positional information correspondence that microwave remote sensor 2 monitors to video image；
4th step：Basic dynamic traffic Parameter fusion, can examine from video sensor 1 and microwave remote sensor 2 simultaneously
Survey the basic traffic parameter such as the traffic flow on section, average speed, occupation rate, queue length and carry out fusion treatment, draw more
Accurately and reliably traffic flow parameter.The fusion results of this level are the inputs of next emerging system simultaneously, this multi-level
Emerging system structure design, be advantageously implemented multi-main-body cooperating information processing, the processing load of each processing center can be disperseed,
Be conducive to improving system effectiveness.
For same object of observation, the result of different sensors output can be different, is not having the situation of priori
Under, take following methods to carry out data fusion so that the detection data providing being capable of mean value error minimum；
Using adaptive optimal Weighted Fusion model, if the traffic flow data variance of two sensors is respectively σ1、σ2, institute
True value to be estimated is X, and the measured value of each sensor is respectively X1, X2, they are independent each other, and are the unbiased of X
Estimate；The weighter factor of each sensor is respectively W1、W2, then the measured value after fusionFor：
Wherein
The method can require no knowledge about any priori of this two detection measurement data, simply applies multisensor
The detection data providing the minimum data fusion value of mean value error it is possible to merge；
5th step：Data association, differentiates whether the data in different time space is derived from same target, radar and video object
Mated, real target can be defined as by successful match, processed by setting means it is impossible to the target of coupling is it is believed that can not be true
Fixed target is it is impossible to exclude the possibility；Using the distance of target, orientation, relative velocity as parameter, calculate radar target and video
The association angle value of target, when associating angle value and being more than the threshold value setting it is believed that mating；The correlation that same sensor is observed and predicted in succession
Data carries out synthesis and state estimation, and with reference to the checking that data is modified of observing and predicting in other information source, each sensor is passed
The point mark sent is associated, and keeps target is continuously followed the tracks of；
6th step：Target recognition and tracking；Form the spy of a N-dimensional according to a certain target characteristic that different sensors record
Levy vector, often an one-dimensional independent characteristic representing target, is compared with consistent feature, so that it is determined that the classification of target.
New data set is just merged by the end of scan with original data every time, and the observation according to sensor estimates target component,
And estimate the position of target in prediction scanning next time with these；
7th step：Traffic behavior is estimated；Detections of radar, to target, exports three-dimensional coordinate, controls video monitoring output image,
According to video coordinates model and radar and the position relationship of video, using 2 points of lowest distance value d of A, B as matching condition, make
The information obtaining the same object that two sensors detect corresponds to, and goes out for same target with match cognization from synchronous images,
Which kind of the data set of all targets is compared with the behavioral pattern of previously determined possible situation, so that determined behavioral pattern and prison
In viewed area, the state of all targets is mated most, is saved in traffic information platform by same for these information；
Traffic events refer to incident such as vehicle traffic accident, scram, traffic jam etc., these things on road
Part will cause traffic to be blocked when occurring, and will become relatively crowded at this, can be drawn the traffic parameter on basis by the 4th step
Information, when occupation rate increases, speed reduces, and needs to determine whether there is event when density becomes big, needs to process in time.This step
It is the traffic flow parameter after preliminary analysis merge, carry out demonstration and whether there is abnormal traffic event；
In the 7th step, traffic behavior recognition methodss are constructed using Fuzzy Synthetical Decision Model, step is as follows：
A1, traffic behavior are estimated, set up model library, to the traffic abnormity state modeling generally occurring within, are easy to record
Pattern match in behavioral pattern and data base；
A2, monitor in real time pavement state, carry out monitor in real time by microwave remote sensor 2 and video sensor 1；
A3, there is the judgement of situation in monitoring range by radar, if it has not, then return A2 proceeding in real time
Monitoring pavement state, if it has, then enter next step；
A4, the three-dimensional coordinate of outgoing event target, the current synchronous images of video acquisition；Radar and video information merge,
Three-dimensional coordinate is mapped to the radar detection coordinate in synchronous images, sends early warning information, and regarded by video sensor 1
Frequency gathers current synchronous images；
A5, radar and video information merge, and three-dimensional coordinate mapping is obtained the radar detection coordinate in synchronous images；
A6, in world coordinate system, set up the matching relationship of radar detection coordinate and image detection target, from synchronous images
In identify event information；
The information such as the picture of A7, output traffic events type and event vehicle, license plate number are to traffic events and information management
Management platform 9.
The superiority of information fusion can be described as the robustness of computing, the coverage of expansion space and time, and increase is estimated
The credibility of meter, improves detection performance, improves space resolution capability, make full use of resource and the scheduling system of multisensor,
Limits play the utilization rate of resource and improve the survival ability of multisensor syste.
The present invention uses hierarchical fusion algorithm, in the pretreatment link of system, abnormal data is rejected, in traffic ginseng
Number collection link and traffic behavior are estimated to carry out data fusion respectively, improve the robustness of system.This technological incorporation is accurately
Multidimensional information, particularly in the case that information has uncertainty, with respect to single-sensor data processing be to single
The process that the obtained data of sensor or information are carried out, it is understood that there may be partly imperfect or insecure information, multisensor
Data fusion can comprehensively utilize multi-sensor information effectively, such that it is able to obtain detected target and environment to a great extent
More accurate, complete information and conforming description or understanding.
In the present invention, video and radar complex, using constituting radar video multisensor syste, using message complementary sense, pass through
Data fusion technique, becomes detection means of tracking that is separate and supplementing each other, it is possible to increase system reliability can provide
Accurate estimation to target location；Fusion treatment is carried out by the telecommunication flow information that each sensor detects, obtains more accurate
Ground data, provides strong parameter for relevant department；Supplemented by the evidence obtaining of video based on detections of radar, to traffic behavior shape
State is estimated, event information is carried out with alarm and captures evidence obtaining；
The present invention proposes fusion method based on microwave and video data, by entering to the initial data of both sensors
After row pretreatment, through space-time uniformity, draw standardized characteristic information；In data fusion module, by using based on power
The decision making level data fusion method of value, exports more accurate telecommunication flow information；Microwave remote sensor 2 detects typing in data base
Some traffic behaviors after, control video sensor 1 to be taken pictures, then be analyzed whether mating with data base, reported to the police,
Reduce false alarm rate, reduce manpower and materials, be truly realized intellectualized detection.
Finally it should be noted that：The foregoing is only the preferred embodiments of the present invention, be not limited to the present invention,
Although being described in detail to the present invention with reference to the foregoing embodiments, for a person skilled in the art, it still may be used
To modify to the technical scheme described in foregoing embodiments, or equivalent is carried out to wherein some technical characteristics.
All any modification, equivalent substitution and improvement within the spirit and principles in the present invention, made etc., should be included in the present invention's
Within protection domain.
Claims (6)
1. a kind of Vehicle Detection device being merged based on microwave and video data it is characterised in that：Described device includes video and passes
Sensor, microwave remote sensor, A/D modular converter, processor module, network communication module, traffic flow parameter data fusion module, friendship
Through-flow management platform, target tracking module, traffic events and information management platform；
Described video sensor is connected with described A/D modular converter respectively with described microwave remote sensor, video sensor and micro-
The non-electric charge quantity signalling of the different characteristic of wave sensor output, being then passed through that described A/D modular converter converts them to can be by counting
The digital quantity that calculation machine is processed；Described A/D modular converter is connected with described processor module, described processor module and described network
Communication module connects, and described processor module is converted at the data of digital quantity to via described A/D module processing
Reason, filters some abnormal datas to obtain useful signal, useful signal is transmitted by described network communication module again；
Described network communication module is connected with described traffic flow parameter data fusion module, described target tracking module respectively,
Useful signal is transferred to described traffic flow parameter data fusion module, described target tracking module by described network communication module；
Described traffic flow parameter data fusion module and described traffic flow management platform connect, described traffic flow parameter data fusion
Module carries out space-time uniformity, feature extraction to useful signal, and carries out data fusion calculating by certain rule to characteristic quantity,
Afterwards fusion results are exported to described traffic flow management platform；
Described target tracking module and traffic events are connected with information management platform, and described target tracking module is entered to useful signal
Row space-time uniformity, feature extraction, and by certain rule, data fusion calculating is carried out to characteristic quantity, finally fusion results are exported
To described information management platform.
2. a kind of Vehicle Detection method being merged based on microwave and video data is it is characterised in that comprise the steps of：
The first step：Detection, carries out background noise suppression, output traffic flow, averagely speed respectively in two sensors detection zone
Degree, occupation rate, queue length and other instant messages；
Second step：Initial data pretreatment, is standardized and carries out pretreatment to multigroup sensing data of input, after satisfaction
The continuous estimation and processor module requirement to amount of calculation and computation sequence；
Grubbs statistical method is adopted for abnormal data preprocess method；
3rd step：Space-time is calibrated, and calibrates time and the spatial reference point of unified each sensor, snaps to the same time in time
Benchmark, spatially it is transformed into the same coordinate system, set up coordinate corresponding relation so that the result after processing seems data fusion
It is the same that processing center station is gathered；If each sensor is independently asynchronous working over time and space, when must carry out
Between move and coordinate transform, merge required unified time and spatial reference point to be formed；By obtaining to single sensor
The estimated information of position and identity category merged, obtain more accurate the estimating of target location, state and identity category
Meter；
4th step：Basic dynamic traffic Parameter fusion, can detect section from video sensor and microwave remote sensor simultaneously
On traffic flow, average speed, occupation rate, the basic traffic parameter such as queue length carry out fusion treatment, draw and more accurately may be used
The traffic flow parameter leaning on；The fusion results of this level are the inputs of next emerging system simultaneously；
5th step：Data association, differentiates whether the data in different time space is derived from same target, and radar is carried out with video object
Coupling, can be defined as real target by successful match, process by setting means it is impossible to the target of coupling is it is believed that unascertainable
Target is it is impossible to exclude the possibility；Using the distance of target, orientation, relative velocity as parameter, calculate radar target and video object
Association angle value, when associate angle value be more than set threshold value when it is believed that coupling；The related data that same sensor is observed and predicted in succession
Carry out synthesis and state estimation, and with reference to the checking that data is modified of observing and predicting in other information source, the transmission of each sensor is come
Point mark be associated, keep target is continuously followed the tracks of；
6th step：Target recognition and tracking；According to a certain target characteristic that different sensors record formed the feature of a N-dimensional to
Amount, often an one-dimensional independent characteristic representing target, is compared with consistent feature, so that it is determined that the classification of target.Every time
New data set is just merged by the end of scan with original data, and the observation according to sensor estimates target component, is used in combination
These estimate the position of target in prediction scanning next time；
7th step：Traffic behavior is estimated；Detections of radar, to target, exports three-dimensional coordinate, controls video monitoring output image, according to
The position relationship of video coordinates model and radar and video, using 2 points of lowest distance value d of A, B as matching condition so that two
The information of the same object that individual sensor detects corresponds to, and is gone out for same target with match cognization from synchronous images.By institute
The data set having target compared with the behavioral pattern of previously determined possible situation, so that determined which kind of behavioral pattern and surveillance zone
In domain, the state of all targets is mated most, is saved in traffic information platform by same for these information.
3. a kind of Vehicle Detection method being merged based on microwave and video data according to claim 2 it is characterised in that：
In described second step, described specific as follows with Grubbs statistical method for abnormal data preprocess method：
Calculate each detection data Z of outputiAverage
Calculate standard deviation
Calculate Grubbs statistic
Given according to data volume n, significant level a=0.05, by look-up table find out Grubbs statistic marginal value T (n,
A), it is compared with T；It is small probability event according to P [T >=T (n, a)]=a, give up T >=T (n, data a).
4. a kind of Vehicle Detection method being merged based on microwave and video data according to claim 2 it is characterised in that：
In described 3rd step, the establishment step of coordinate corresponding relation is as follows：
First, calculate the inner parameter of video sensor using calibration technique, set up video sensor coordinate model；
Secondly, according to the position relationship between video sensor coordinate model and microwave remote sensor and video sensor, set up
Coordinate pair in video sensor acquired image plane for the target that under world coordinate system, microwave remote sensor is monitored should
Relation；
Finally, the information of microwave remote sensor just can be realized according to coordinate corresponding relation and video information is merged, realize micro-
The 3D world coordinates that wave sensor detects is converted into corresponding 2D image coordinate p ' (u ', v ') in video image, to make full use of
The positional information correspondence that microwave remote sensor monitors is to video image.
5. a kind of Vehicle Detection method being merged based on microwave and video data according to claim 2 it is characterised in that：
In described 4th step, for same object of observation, the result of different sensors output can be different, is not having priori
In the case of, take following methods to carry out data fusion：
Using adaptive optimal Weighted Fusion model, if the traffic flow data variance of two sensors is respectively σ1、σ2, estimate
The true value of meter is X, and the measured value of each sensor is respectively X1、X2, they are independent each other, and are the unbiased esti-mator of X；
The weighter factor of each sensor is respectively W1、W2, then the measured value after fusionFor：
Wherein
The detection data that the method application multisensor provides, merges and the minimum data fusion value of mean value error.
6. a kind of Vehicle Detection method being merged based on microwave and video data according to claim 2 it is characterised in that：
Fuzzy Synthetical Decision Model is adopted to construct a traffic events recognizer in described 7th step, step is as follows：
A1, traffic behavior are estimated, set up model library, to the traffic abnormity state modeling generally occurring within, are easy to the behavior recording
Pattern match in pattern and data base；
A2, monitor in real time pavement state, carry out monitor in real time by microwave remote sensor 2 and video sensor 1；
A3, there is the judgement of situation in monitoring range by radar, if it has not, then returning A2 to proceed monitor in real time
Pavement state, if it has, then enter next step；
A4, the three-dimensional coordinate of outgoing event target, the current synchronous images of video acquisition；Radar and video information merge, by three
Dimension coordinate is mapped to the radar detection coordinate in synchronous images, sends early warning information, and carries out video by video sensor 1 and adopt
Collect current synchronous images；
A5, radar and video information merge, and three-dimensional coordinate mapping is obtained the radar detection coordinate in synchronous images；
A6, in world coordinate system, set up the matching relationship of radar detection coordinate and image detection target, know from synchronous images
Other outgoing event information；
The information such as the picture of A7, output traffic events type and event vehicle, license plate number are to traffic events and information management management
Platform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610952272.0A CN106408940B (en) | 2016-11-02 | 2016-11-02 | Traffic detection method and device based on microwave and video data fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610952272.0A CN106408940B (en) | 2016-11-02 | 2016-11-02 | Traffic detection method and device based on microwave and video data fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106408940A true CN106408940A (en) | 2017-02-15 |
| CN106408940B CN106408940B (en) | 2023-04-14 |
Family
ID=58014428
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610952272.0A Active CN106408940B (en) | 2016-11-02 | 2016-11-02 | Traffic detection method and device based on microwave and video data fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106408940B (en) |
Cited By (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107680054A (en) * | 2017-09-26 | 2018-02-09 | 长春理工大学 | Multisource image anastomosing method under haze environment |
| CN108734959A (en) * | 2018-04-28 | 2018-11-02 | 扬州远铭光电有限公司 | A kind of embedded vision train flow analysis method and system |
| CN108922188A (en) * | 2018-07-24 | 2018-11-30 | 河北德冠隆电子科技有限公司 | The four-dimensional outdoor scene traffic of radar tracking positioning perceives early warning monitoring management system |
| CN108961790A (en) * | 2018-07-24 | 2018-12-07 | 河北德冠隆电子科技有限公司 | Bad weather pre-warning management system and method based on four-dimensional outdoor scene traffic simulation |
| CN109343051A (en) * | 2018-11-15 | 2019-02-15 | 众泰新能源汽车有限公司 | A kind of multi-Sensor Information Fusion Approach driven for advanced auxiliary |
| CN109613537A (en) * | 2019-01-16 | 2019-04-12 | 南京奥杰智能科技有限公司 | A kind of hologram radar |
| CN109615866A (en) * | 2019-01-16 | 2019-04-12 | 南京奥杰智能科技有限公司 | Traffic monitoring system Internet-based |
| CN109671278A (en) * | 2019-03-02 | 2019-04-23 | 安徽超远信息技术有限公司 | A kind of bayonet precise positioning grasp shoot method and device based on multiple target radar |
| CN110126885A (en) * | 2018-02-02 | 2019-08-16 | 保定市天河电子技术有限公司 | A kind of railway circumference intrusion target monitoring method and system |
| CN110163270A (en) * | 2019-05-10 | 2019-08-23 | 北京易控智驾科技有限公司 | Multi-Sensor Information Fusion Approach and system |
| CN110444026A (en) * | 2019-08-06 | 2019-11-12 | 北京万集科技股份有限公司 | The triggering grasp shoot method and system of vehicle |
| CN110640737A (en) * | 2018-11-07 | 2020-01-03 | 宁波赛朗科技有限公司 | Industrial robot for measuring data fusion attitude |
| CN110796868A (en) * | 2019-12-02 | 2020-02-14 | 江苏中路工程技术研究院有限公司 | Video and microwave integrated traffic incident monitoring system and method |
| CN110865367A (en) * | 2019-11-30 | 2020-03-06 | 山西禾源科技股份有限公司 | Intelligent fusion method for radar video data |
| CN110969059A (en) * | 2018-09-30 | 2020-04-07 | 长城汽车股份有限公司 | Lane line identification method and system |
| CN111209327A (en) * | 2020-01-14 | 2020-05-29 | 南京悠淼科技有限公司 | Multi-sensor distributed sensing interconnection and edge fusion processing system and method |
| CN111477010A (en) * | 2020-04-08 | 2020-07-31 | 图达通智能科技(苏州)有限公司 | Device for intersection holographic sensing and control method thereof |
| CN112150799A (en) * | 2020-08-19 | 2020-12-29 | 上海图丽信息技术有限公司 | Method for collecting road vehicle traffic big data by fusing radar videos |
| CN112150797A (en) * | 2020-08-19 | 2020-12-29 | 上海图丽信息技术有限公司 | Traffic incident detection method fusing radar videos |
| CN112148769A (en) * | 2020-09-15 | 2020-12-29 | 浙江大华技术股份有限公司 | Data synchronization method, device, storage medium and electronic device |
| CN112509331A (en) * | 2020-12-18 | 2021-03-16 | 芜湖易来达雷达科技有限公司 | Verification system and verification method for traffic radar data |
| CN112532934A (en) * | 2020-11-23 | 2021-03-19 | 国网山东省电力公司利津县供电公司 | Multi-dimensional cooperative monitoring system |
| CN112731324A (en) * | 2020-12-16 | 2021-04-30 | 中交第一公路勘察设计研究院有限公司 | Multi-radar cross-regional networking multi-target tracking method for expressway |
| CN112837529A (en) * | 2019-11-25 | 2021-05-25 | 斑马智行网络(香港)有限公司 | Data processing method and system, acquisition device, processor and storage medium |
| CN113255708A (en) * | 2020-02-10 | 2021-08-13 | 富士通株式会社 | Data fusion method and device and data processing equipment |
| CN113393676A (en) * | 2021-06-09 | 2021-09-14 | 东北林业大学 | Traffic detection method and device based on unmanned aerial vehicle vision and millimeter wave radar |
| CN113412506A (en) * | 2019-02-13 | 2021-09-17 | 日立安斯泰莫株式会社 | Vehicle control device and electronic control system |
| CN113689691A (en) * | 2020-05-18 | 2021-11-23 | 富士通株式会社 | Traffic detection system |
| CN114530042A (en) * | 2021-12-31 | 2022-05-24 | 威海南海数字产业研究院有限公司 | Urban traffic brain monitoring system based on internet of things technology |
| CN114814720A (en) * | 2022-06-20 | 2022-07-29 | 成都市克莱微波科技有限公司 | Microwave direction finding device, system, method and storage medium |
| CN115278361A (en) * | 2022-07-20 | 2022-11-01 | 重庆长安汽车股份有限公司 | Driving video data extraction method, system, medium and electronic equipment |
| CN115376312A (en) * | 2022-07-22 | 2022-11-22 | 交通运输部路网监测与应急处置中心 | Road monitoring method and system based on radar and video fusion |
| CN111582130B (en) * | 2020-04-30 | 2023-04-28 | 长安大学 | Traffic behavior perception fusion system and method based on multi-source heterogeneous information |
| CN117636671A (en) * | 2024-01-24 | 2024-03-01 | 四川君迪能源科技有限公司 | Cooperation scheduling method and system for intelligent vehicle meeting of rural roads |
| US11934746B2 (en) | 2017-10-25 | 2024-03-19 | Ihi Corporation | Information generation device |
| CN118013465A (en) * | 2024-04-09 | 2024-05-10 | 微网优联科技(成都)有限公司 | Non-motor vehicle identification method and system based on multi-sensor cooperation |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1940591A (en) * | 2005-09-26 | 2007-04-04 | 通用汽车环球科技运作公司 | System and method of target tracking using sensor fusion |
| CN101226689A (en) * | 2008-02-03 | 2008-07-23 | 北京交通大学 | Multi-sensor access device for acquisition of road traffic information and data fusion method thereof |
| WO2008142680A2 (en) * | 2007-05-20 | 2008-11-27 | Rafael Advanced Defense Systems Ltd | Tracking and imaging data fusion |
| CN101318491A (en) * | 2008-05-14 | 2008-12-10 | 合肥工业大学 | Built-in integrated visual sensation auxiliary driving safety system |
| CN101655561A (en) * | 2009-09-14 | 2010-02-24 | 南京莱斯信息技术股份有限公司 | Federated Kalman filtering-based method for fusing multilateration data and radar data |
| CN101751782A (en) * | 2009-12-30 | 2010-06-23 | 北京大学深圳研究生院 | Crossroad traffic event automatic detection system based on multi-source information fusion |
| CN102542843A (en) * | 2010-12-07 | 2012-07-04 | 比亚迪股份有限公司 | Early warning method for preventing vehicle collision and device |
| CN102881162A (en) * | 2012-09-29 | 2013-01-16 | 北京市交通信息中心 | Data processing and fusion method for large-scale traffic information |
| CN103093625A (en) * | 2013-01-09 | 2013-05-08 | 杭州师范大学 | City road traffic condition real-time estimation method based on reliability verification |
| CN103116981A (en) * | 2011-11-17 | 2013-05-22 | 无锡物联网产业研究院 | Multi-sensor system and information fusion method |
| US20140195138A1 (en) * | 2010-11-15 | 2014-07-10 | Image Sensing Systems, Inc. | Roadway sensing systems |
| CN104123837A (en) * | 2013-04-28 | 2014-10-29 | 上海济祥智能交通科技有限公司 | Interrupted flow travel time estimation method based on microwave and video data fusion |
| CN104200657A (en) * | 2014-07-22 | 2014-12-10 | 杭州智诚惠通科技有限公司 | Traffic flow parameter acquisition method based on video and sensor |
| CN104933879A (en) * | 2014-03-19 | 2015-09-23 | 北京航天长峰科技工业集团有限公司 | Traffic information collecting, inducing and publishing method based on Internet of Things |
| CN105015411A (en) * | 2015-07-03 | 2015-11-04 | 河南工业技术研究院 | Automobile microwave radar anti-collision early-warning method and system based on video fusion |
| CN105334514A (en) * | 2015-10-19 | 2016-02-17 | 上海无线电设备研究所 | Tramcar radar video compound early warning crashproof system and method |
| CN105427619A (en) * | 2015-12-24 | 2016-03-23 | 上海新中新猎豹交通科技股份有限公司 | Vehicle following distance automatic recording system and method |
| CN105807280A (en) * | 2016-04-26 | 2016-07-27 | 南京鹏力***工程研究所 | Echo fused target track association method based on track state estimation |
-
2016
- 2016-11-02 CN CN201610952272.0A patent/CN106408940B/en active Active
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1940591A (en) * | 2005-09-26 | 2007-04-04 | 通用汽车环球科技运作公司 | System and method of target tracking using sensor fusion |
| WO2008142680A2 (en) * | 2007-05-20 | 2008-11-27 | Rafael Advanced Defense Systems Ltd | Tracking and imaging data fusion |
| CN101226689A (en) * | 2008-02-03 | 2008-07-23 | 北京交通大学 | Multi-sensor access device for acquisition of road traffic information and data fusion method thereof |
| CN101318491A (en) * | 2008-05-14 | 2008-12-10 | 合肥工业大学 | Built-in integrated visual sensation auxiliary driving safety system |
| CN101655561A (en) * | 2009-09-14 | 2010-02-24 | 南京莱斯信息技术股份有限公司 | Federated Kalman filtering-based method for fusing multilateration data and radar data |
| CN101751782A (en) * | 2009-12-30 | 2010-06-23 | 北京大学深圳研究生院 | Crossroad traffic event automatic detection system based on multi-source information fusion |
| US20140195138A1 (en) * | 2010-11-15 | 2014-07-10 | Image Sensing Systems, Inc. | Roadway sensing systems |
| CN102542843A (en) * | 2010-12-07 | 2012-07-04 | 比亚迪股份有限公司 | Early warning method for preventing vehicle collision and device |
| CN103116981A (en) * | 2011-11-17 | 2013-05-22 | 无锡物联网产业研究院 | Multi-sensor system and information fusion method |
| CN102881162A (en) * | 2012-09-29 | 2013-01-16 | 北京市交通信息中心 | Data processing and fusion method for large-scale traffic information |
| CN103093625A (en) * | 2013-01-09 | 2013-05-08 | 杭州师范大学 | City road traffic condition real-time estimation method based on reliability verification |
| CN104123837A (en) * | 2013-04-28 | 2014-10-29 | 上海济祥智能交通科技有限公司 | Interrupted flow travel time estimation method based on microwave and video data fusion |
| CN104933879A (en) * | 2014-03-19 | 2015-09-23 | 北京航天长峰科技工业集团有限公司 | Traffic information collecting, inducing and publishing method based on Internet of Things |
| CN104200657A (en) * | 2014-07-22 | 2014-12-10 | 杭州智诚惠通科技有限公司 | Traffic flow parameter acquisition method based on video and sensor |
| CN105015411A (en) * | 2015-07-03 | 2015-11-04 | 河南工业技术研究院 | Automobile microwave radar anti-collision early-warning method and system based on video fusion |
| CN105334514A (en) * | 2015-10-19 | 2016-02-17 | 上海无线电设备研究所 | Tramcar radar video compound early warning crashproof system and method |
| CN105427619A (en) * | 2015-12-24 | 2016-03-23 | 上海新中新猎豹交通科技股份有限公司 | Vehicle following distance automatic recording system and method |
| CN105807280A (en) * | 2016-04-26 | 2016-07-27 | 南京鹏力***工程研究所 | Echo fused target track association method based on track state estimation |
Non-Patent Citations (1)
| Title |
|---|
| 刘志强;程红星;王运霞;: "车辆防撞检测技术研究" * |
Cited By (42)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107680054A (en) * | 2017-09-26 | 2018-02-09 | 长春理工大学 | Multisource image anastomosing method under haze environment |
| US11934746B2 (en) | 2017-10-25 | 2024-03-19 | Ihi Corporation | Information generation device |
| CN110126885A (en) * | 2018-02-02 | 2019-08-16 | 保定市天河电子技术有限公司 | A kind of railway circumference intrusion target monitoring method and system |
| CN108734959A (en) * | 2018-04-28 | 2018-11-02 | 扬州远铭光电有限公司 | A kind of embedded vision train flow analysis method and system |
| CN108922188A (en) * | 2018-07-24 | 2018-11-30 | 河北德冠隆电子科技有限公司 | The four-dimensional outdoor scene traffic of radar tracking positioning perceives early warning monitoring management system |
| CN108961790A (en) * | 2018-07-24 | 2018-12-07 | 河北德冠隆电子科技有限公司 | Bad weather pre-warning management system and method based on four-dimensional outdoor scene traffic simulation |
| CN110969059A (en) * | 2018-09-30 | 2020-04-07 | 长城汽车股份有限公司 | Lane line identification method and system |
| CN110640737A (en) * | 2018-11-07 | 2020-01-03 | 宁波赛朗科技有限公司 | Industrial robot for measuring data fusion attitude |
| CN109343051A (en) * | 2018-11-15 | 2019-02-15 | 众泰新能源汽车有限公司 | A kind of multi-Sensor Information Fusion Approach driven for advanced auxiliary |
| CN109615866A (en) * | 2019-01-16 | 2019-04-12 | 南京奥杰智能科技有限公司 | Traffic monitoring system Internet-based |
| CN109613537A (en) * | 2019-01-16 | 2019-04-12 | 南京奥杰智能科技有限公司 | A kind of hologram radar |
| CN113412506B (en) * | 2019-02-13 | 2023-06-13 | 日立安斯泰莫株式会社 | Vehicle control device and electronic control system |
| CN113412506A (en) * | 2019-02-13 | 2021-09-17 | 日立安斯泰莫株式会社 | Vehicle control device and electronic control system |
| CN109671278A (en) * | 2019-03-02 | 2019-04-23 | 安徽超远信息技术有限公司 | A kind of bayonet precise positioning grasp shoot method and device based on multiple target radar |
| CN110163270A (en) * | 2019-05-10 | 2019-08-23 | 北京易控智驾科技有限公司 | Multi-Sensor Information Fusion Approach and system |
| CN110444026B (en) * | 2019-08-06 | 2021-07-09 | 北京万集科技股份有限公司 | Triggering snapshot method and system for vehicle |
| CN110444026A (en) * | 2019-08-06 | 2019-11-12 | 北京万集科技股份有限公司 | The triggering grasp shoot method and system of vehicle |
| CN112837529A (en) * | 2019-11-25 | 2021-05-25 | 斑马智行网络(香港)有限公司 | Data processing method and system, acquisition device, processor and storage medium |
| CN112837529B (en) * | 2019-11-25 | 2022-12-02 | 斑马智行网络(香港)有限公司 | Data processing method and system, acquisition device, processor and storage medium |
| CN110865367B (en) * | 2019-11-30 | 2023-05-05 | 山西禾源科技股份有限公司 | Intelligent radar video data fusion method |
| CN110865367A (en) * | 2019-11-30 | 2020-03-06 | 山西禾源科技股份有限公司 | Intelligent fusion method for radar video data |
| CN110796868A (en) * | 2019-12-02 | 2020-02-14 | 江苏中路工程技术研究院有限公司 | Video and microwave integrated traffic incident monitoring system and method |
| CN111209327A (en) * | 2020-01-14 | 2020-05-29 | 南京悠淼科技有限公司 | Multi-sensor distributed sensing interconnection and edge fusion processing system and method |
| CN113255708A (en) * | 2020-02-10 | 2021-08-13 | 富士通株式会社 | Data fusion method and device and data processing equipment |
| CN111477010A (en) * | 2020-04-08 | 2020-07-31 | 图达通智能科技(苏州)有限公司 | Device for intersection holographic sensing and control method thereof |
| CN111582130B (en) * | 2020-04-30 | 2023-04-28 | 长安大学 | Traffic behavior perception fusion system and method based on multi-source heterogeneous information |
| CN113689691A (en) * | 2020-05-18 | 2021-11-23 | 富士通株式会社 | Traffic detection system |
| CN112150797A (en) * | 2020-08-19 | 2020-12-29 | 上海图丽信息技术有限公司 | Traffic incident detection method fusing radar videos |
| CN112150799A (en) * | 2020-08-19 | 2020-12-29 | 上海图丽信息技术有限公司 | Method for collecting road vehicle traffic big data by fusing radar videos |
| CN112148769A (en) * | 2020-09-15 | 2020-12-29 | 浙江大华技术股份有限公司 | Data synchronization method, device, storage medium and electronic device |
| CN112532934A (en) * | 2020-11-23 | 2021-03-19 | 国网山东省电力公司利津县供电公司 | Multi-dimensional cooperative monitoring system |
| CN112731324A (en) * | 2020-12-16 | 2021-04-30 | 中交第一公路勘察设计研究院有限公司 | Multi-radar cross-regional networking multi-target tracking method for expressway |
| CN112509331A (en) * | 2020-12-18 | 2021-03-16 | 芜湖易来达雷达科技有限公司 | Verification system and verification method for traffic radar data |
| CN113393676A (en) * | 2021-06-09 | 2021-09-14 | 东北林业大学 | Traffic detection method and device based on unmanned aerial vehicle vision and millimeter wave radar |
| CN114530042A (en) * | 2021-12-31 | 2022-05-24 | 威海南海数字产业研究院有限公司 | Urban traffic brain monitoring system based on internet of things technology |
| CN114814720A (en) * | 2022-06-20 | 2022-07-29 | 成都市克莱微波科技有限公司 | Microwave direction finding device, system, method and storage medium |
| CN115278361A (en) * | 2022-07-20 | 2022-11-01 | 重庆长安汽车股份有限公司 | Driving video data extraction method, system, medium and electronic equipment |
| CN115278361B (en) * | 2022-07-20 | 2023-08-01 | 重庆长安汽车股份有限公司 | Driving video data extraction method, system, medium and electronic equipment |
| CN115376312A (en) * | 2022-07-22 | 2022-11-22 | 交通运输部路网监测与应急处置中心 | Road monitoring method and system based on radar and video fusion |
| CN117636671A (en) * | 2024-01-24 | 2024-03-01 | 四川君迪能源科技有限公司 | Cooperation scheduling method and system for intelligent vehicle meeting of rural roads |
| CN117636671B (en) * | 2024-01-24 | 2024-04-30 | 四川君迪能源科技有限公司 | Cooperation scheduling method and system for intelligent vehicle meeting of rural roads |
| CN118013465A (en) * | 2024-04-09 | 2024-05-10 | 微网优联科技(成都)有限公司 | Non-motor vehicle identification method and system based on multi-sensor cooperation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106408940B (en) | 2023-04-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106408940A (en) | Microwave and video data fusion-based traffic detection method and device | |
| WO2020253308A1 (en) | Human-machine interaction behavior security monitoring and forewarning method for underground belt transportation-related personnel | |
| CN113255481B (en) | Crowd state detection method based on unmanned patrol car | |
| CN102811343B (en) | Intelligent video monitoring system based on behavior recognition | |
| Huang et al. | Automatic moving object extraction through a real-world variable-bandwidth network for traffic monitoring systems | |
| CN101552910B (en) | Remnant detection device based on comprehensive computer vision | |
| CN106203274A (en) | Pedestrian's real-time detecting system and method in a kind of video monitoring | |
| CA3094424A1 (en) | Safety monitoring and early-warning method for man-machine interaction behavior of underground conveyor belt operator | |
| Sun et al. | Vehicle reidentification using multidetector fusion | |
| JP5479907B2 (en) | Network monitoring system | |
| CN102254394A (en) | Antitheft monitoring method for poles and towers in power transmission line based on video difference analysis | |
| CN102163290A (en) | Method for modeling abnormal events in multi-visual angle video monitoring based on temporal-spatial correlation information | |
| CN109830078B (en) | Intelligent behavior analysis method and intelligent behavior analysis equipment suitable for narrow space | |
| CN113326719A (en) | Method, equipment and system for target tracking | |
| CN106846297A (en) | Pedestrian's flow quantity detecting system and method based on laser radar | |
| CN114333424B (en) | Bridge prevents ship and hits monitoring early warning system | |
| CN112183472A (en) | Method for detecting whether test field personnel wear work clothes or not based on improved RetinaNet | |
| CN113642403B (en) | Crowd abnormal intelligent safety detection system based on edge calculation | |
| CN110490150A (en) | A kind of automatic auditing system of picture violating the regulations and method based on vehicle retrieval | |
| Ua-Areemitr et al. | Low-cost road traffic state estimation system using time-spatial image processing | |
| CN117312801A (en) | AI-based smart city monitoring system and method | |
| CN115860144A (en) | Machine learning system for anti-electricity-stealing site | |
| CN114708544A (en) | Intelligent violation monitoring helmet based on edge calculation and monitoring method thereof | |
| CN110175521A (en) | Method based on double camera linkage detection supervision indoor human body behavior | |
| CN105471632B (en) | A kind of detection method of autoregression line fault |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |